Tracking and Classifying Objects on a Conveyor Belt Using Time-of-Flight Camera

The ability to obtain 3D information is vital for many applications in construction, manufacturing, and vehicle automation and autonomy. TOF (Time-of-Flight) sensors, which provide depth information at each pixel in addition to intensity, are becoming more widely available and more affordable. This paper examines the applicability of TOF sensors to several real world problems that can be relevant in automated assembly or sorting applications. The setting is an indoor environment, and the experiments investigate the ability of TOF sensors to provide sensing for a robot whose task is to handle products moving on a conveyor belt. The range information is used to compute the dimensions of- and to recognizeobjects moving on a conveyor belt. The geometric and recognition information is then passed on to the robot for further action. The results indicate that there are immediate opportunities for the use of TOF sensors in automating such applications.

[1]  Kwang Nam Choi,et al.  Real-Time Object Recognition and Modeling for Heavy-Equipment Operation , 2008 .

[2]  Hyojoo Son,et al.  Rapid 3D Object Modeling Using 3D Data from Flash LADAR for Automated Construction Equipment Operations , 2009 .

[3]  Alexander M. Bronstein,et al.  Three-Dimensional Face Recognition , 2005, International Journal of Computer Vision.

[4]  M. A. Khaboua,et al.  Shape recognition using eigenvalues of the Dirichlet Laplacian , 2006 .

[5]  Andrew E. Johnson,et al.  Using Spin Images for Efficient Object Recognition in Cluttered 3D Scenes , 1999, IEEE Trans. Pattern Anal. Mach. Intell..

[6]  Jochen Teizer,et al.  Human Motion Analysis Using 3D Range Imaging Technology , 2009 .

[7]  T. Bock,et al.  Automation and Robotics in Construction ( ISARC 2010 ) INDIVIDUALIZATION OF DESIGN VARIATION IN CONSTRUCTION , 2011 .

[8]  Nico Blodow,et al.  Persistent Point Feature Histograms for 3D Point Clouds , 2008 .

[9]  Igor Guskov,et al.  3D object recognition from range images using pyramid matching , 2007, 2007 IEEE 11th International Conference on Computer Vision.

[10]  Carlos H. Caldas,et al.  Real-Time Three-Dimensional Occupancy Grid Modeling for the Detection and Tracking of Construction Resources , 2007 .

[11]  Jitendra Malik,et al.  Recognizing Objects in Range Data Using Regional Point Descriptors , 2004, ECCV.

[12]  Patrick J. Flynn,et al.  A Survey Of Free-Form Object Representation and Recognition Techniques , 2001, Comput. Vis. Image Underst..

[13]  G. Ziegler,et al.  High-Quality Reconstruction from Multiview Video Streams , 2007, IEEE Signal Processing Magazine.

[14]  Jochen Teizer.  3D range imaging camera sensing for active safety in construction , 2008, J. Inf. Technol. Constr..

[15]  Mohammed Bennamoun,et al.  Three-Dimensional Model-Based Object Recognition and Segmentation in Cluttered Scenes , 2006, IEEE Transactions on Pattern Analysis and Machine Intelligence.

[16]  Rasmus Larsen,et al.  Cluster tracking with Time-of-Flight cameras , 2008, 2008 IEEE Computer Society Conference on Computer Vision and Pattern Recognition Workshops.

[17]  Mohamed A. Khabou,et al.  Shape recognition using eigenvalues of the Dirichlet Laplacian , 2007, Pattern Recognit..

[18]  Niklas Peinecke,et al.  Laplace-Beltrami spectra as 'Shape-DNA' of surfaces and solids , 2006, Comput. Aided Des..

[19]  Seokho Chi,et al.  Object identification based on 3D spatial models of construction sites , 2007 .